{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T10:16:22Z","timestamp":1755598582146,"version":"3.28.0"},"reference-count":12,"publisher":"IEEE Comput. Soc","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1109\/tai.2002.1180839","type":"proceedings-article","created":{"date-parts":[[2003,6,26]],"date-time":"2003-06-26T15:35:00Z","timestamp":1056641700000},"page":"463-468","source":"Crossref","is-referenced-by-count":3,"title":["Cooperative co-learning: a model-based approach for solving multi-agent reinforcement problems"],"prefix":"10.1109","author":[{"given":"B.","family":"Scherrer","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"F.","family":"Charpillet","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"A Heuristic Approach for Solving Decentralized-POMDP Assessment on the Pursuit Problem Rapport de recherche","year":"2001","author":"chad\u00e8s","key":"ref4"},{"key":"ref3","article-title":"Sequential optimality and coordination in multiagent systems","author":"boutilier","year":"1999","journal-title":"the Seventeenth International Joint Conference on Artificial Intelligence"},{"journal-title":"The optimal control of partially observable Markov Decision Processes","year":"1971","author":"sondik","key":"ref10"},{"key":"ref6","first-page":"313","article-title":"Co-evolving parasites improve simulated evolution as an optimization procedure","volume":"x","author":"hillis","year":"1992","journal-title":"Artificial Life II"},{"journal-title":"Machine Learning","year":"1992","author":"watkins","key":"ref11"},{"key":"ref5","first-page":"506","article-title":"Co-evolution of pursuit and evasion II: Simulation methods and results","author":"cliff","year":"1996","journal-title":"From Animals to Animats 4"},{"journal-title":"Experiments with an algorithm which learns stochastic memoryless policies for POMDPs","year":"1999","author":"williams","key":"ref12"},{"key":"ref8","first-page":"307","author":"peshkin","year":"1999","journal-title":"Learning policies with external memory"},{"key":"ref7","first-page":"323","article-title":"Using eligibility traces to find the best memoryless policy in partially observable Markov Decision Processes","author":"loch","year":"1998","journal-title":"Proc 15th International Conf on Machine Learning"},{"key":"ref2","article-title":"The complexity of decentralized control of Markov Decision Processes","author":"bernstein","year":"2000","journal-title":"the Sixteenth Conference on Uncertainty in Artificial Intelligence"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","author":"puterman","year":"1994","journal-title":"Markov Decision Processes"},{"key":"ref1","article-title":"Direct gradient-based reinforcement learning","author":"baxter","year":"1999","journal-title":"Technical Report"}],"event":{"name":"14th IEEE International Conference on Tools with Artificial Intelligence (ICTAI 2002)","acronym":"TAI-02","location":"Washington, DC, USA"},"container-title":["14th IEEE International Conference on Tools with Artificial Intelligence, 2002. (ICTAI 2002). Proceedings."],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/8408\/26514\/01180839.pdf?arnumber=1180839","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,15]],"date-time":"2017-06-15T22:46:23Z","timestamp":1497566783000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/1180839\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"references-count":12,"URL":"https:\/\/doi.org\/10.1109\/tai.2002.1180839","relation":{},"subject":[]}}